Stock price prediction is a challenging and dynamic task due to the high volatility and complexity of financial markets. In this study, we present a comparative analysis of several machine learning algorithms applied to the prediction of stock prices. The models explored include Gradient Boosting Regressor (GBR), Gated Recurrent Unit (GRU), Linear Regression (LR), Long Short-Term Memory (LSTM), Random Forest (RF), and Support Vector Regression (SVR). Using a dataset comprising historical stock prices from multiple companies, we evaluate the performance of each model based on accuracy and predictive stability. Daily predictions were generated for each model, and the results were assessed using metrics such as average deviation from real price. The analysis indicates that while deep learning models like GRU and LSTM exhibit a strong capacity to capture temporal patterns, ensemble methods such as GBR and RF also provide competitive accuracy for short-term forecasts. This research highlights the strengths and limitations of various approaches to stock price forecasting and offers insights into their potential applications for investment decision-making. Future work may involve extending this analysis to broader financial datasets and investigating the integration of additional market factors.

Flow-based machine-learning detectors can analyse encrypted or payload-inaccessible traffic, but their aggregate scores can conceal severe failures on rare attacks. This study compares seven supervised classifiers on CSE-CIC-IDS2018 using a seven-class label space: Benign, Bot, Brute Force, distributed denial of service (DDoS), denial of service (DoS), Infiltration, and Web Attack. The evaluation combined numeric cleaning, a stratified 70/15/15 split, low-variance feature selection, and Borderline-SMOTE for selected training classes. Gaussian naive Bayes, logistic regression, random forest, XGBoost, LightGBM, CatBoost, and a multilayer perceptron were evaluated on 2,434,942 held-out flows. Random forest produced the highest macro F1-score (0.7841), followed by LightGBM (0.7683), while their weighted F1-scores were 0.9815 and 0.9825, respectively. The gap between macro and weighted measures exposes weak recognition of minority classes: even the best overall model achieved F1-scores of only 0.2106 for Infiltration and 0.4659 for Web Attack. A complementary prototype captures rotating packet traces, extracts bidirectional flow features with CICFlowMeter, aligns them with the training schema, and reports predicted labels and confidence values. Under this fixed protocol, tree ensembles were strongest among the tested configurations, but the results do not establish general superiority or deployment readiness. The prototype remains a proof-of-concept inference pipeline.

This paper discusses the development and application of linear regression (LR) to predict stock prices in the stock market. The main objective is to analyse the efficiency and accuracy of linear regression in relation to financial markets, and specifically to predict stock prices one day ahead. The paper begins with a detailed review of the related theoretical foundations and existing methods in the field of stock market forecasting. Next, it discusses the formulation of the stock price forecasting problem and the choice of linear regression as a tool to solve it. Particular emphasis is placed on understanding the properties of linear regression and its potential contribution to predictive models. The second part of the paper describes the implementation and testing of the LR algorithm, including the design and execution of experiments to evaluate its performance. The results are analysed using graphs and individual numerical predictions that were collected on a sample of multiple firm stocks. These results are described and discussed in detail, assessing their sensitivity to short-term volatility and deviation from fair value. The paper provides a new perspective on the use of linear regression in forecasting stock markets and contributes to a better understanding of its effectiveness and limitations.

The volatility of cryptocurrencies poses challenges for accurate price forecasting. This study compares traditional machine learning models (Linear Regression, Support Vector Regression), ensemble methods (Random Forest, Gradient Boosting), and deep learning architectures (LSTM, GRU) in predicting the daily prices of Bitcoin (BTC), Ethereum (ETH), Cardano (ADA), Ripple (XRP), and Polkadot (DOT). Using historical data from CoinGecko, a sliding window, and normalisation, we assess models by Root Mean Square Error (RMSE) and relative percentage error. Results show that LSTM and GRU achieve the best overall accuracy, while Linear Regression remains competitive for stable assets such as BTC, ADA, and DOT. Ensemble methods performed moderately, whereas SVR consistently underperformed. The findings underline the importance of matching prediction models to the characteristics of specific cryptocurrencies.

Post-quantum cryptography represents one of the most promising areas of modern cryptography. The development in this discipline significantly accelerated after it became of interest to the National Institute of Standards and Technology (NIST). One of the important research directions in this area is the practical deployment of post-quantum cryptographic algorithms on resource-constrained devices. In this article, we investigate the possibility of deploying post-quantum cryptography on small processors with limited random access memory (RAM) capacity. These processors are commonly used in Internet of Things (IoT) devices, where the practical deployment of post-quantum algorithms remains challenging due to computational and memory constraints. We select a suitable algorithm and perform several implementation modifications that enable its execution on microcontrollers with limited memory resources.